Statistical Learning
Robust Mean Estimation Without Moments for Symmetric Distributions
Moreover, the guarantees that they achieve in the heavy-tailed setting are weaker than those for sub-Gaussian distributions with known covariance.
Data Selection for Language Models via Importance Resampling
Selecting a suitable pretraining dataset is crucial for both general-domain (e.g., GPT -
Partial Label Learning with Dissimilarity Propagation guided Candidate Label Shrinkage
The code is publicly available at https://github.com/Yangfc-ML/DPCLS .
Characteristic Circuits
In many real-world scenarios, it is crucial to be able to reliably and efficiently reason under uncertainty while capturing complex relationships in data.
A Randomized Approach to Tight Privacy Accounting
Bounding privacy leakage over compositions, i.e., privacy accounting, is a key challenge in differential privacy (DP).
